Generic GA-based meta-level parameter optimization for pattern recognition systems

This paper proposes a novel generic meta-level parameter optimization framework to address the problem of determining the optimal parameters of pattern recognition systems. The proposed framework is currently implemented to control the parameters of neuro-fuzzy system, a subclass of pattern recognition system, by employing a genetic algorithm (GA) as the core optimization technique. Two neuro-fuzzy systems i.e., generic self-organizing fuzzy neural network realizing Yager inference (GenSoFNN-Yager) and reduced fuzzy cerebellar model articulation computer realizing the Yager inference (RFCMAC-Yager), are employed as the test prototypes to evaluate the proposed framework. Experimental results on several classification and regression problems have shown the efficacy and robustness of the proposed approach.